The government of China seeks to improve e-government service quality and build a serviceoriented government that citizens find satisfactory. To this end, big data is being used as a new tool of government service innovation. However, there is a lack of research on how big data affects the performance of government smart services. This article explores the influence mechanisms of government big data capabilities on the performance of smart service provision, utilizing the carding analysis of relevant literature, published both in China and abroad. To this end, a structural equation model was constructed. Using data from 289 valid questionnaires in Jiangsu, Shandong, Zhejiang, and other provinces and cities in China, the study tests internal mechanisms of big data capabilities and its effect on smart service performance. Following a new definition of government big data capability, the paper divides the capability into three dimensions: big data system capability, big data human capability and big data management capability. The main conclusions are as follows: (1) Big data management capability has a significant positive impact on big data human capability and big data system capability. (2) Big data system capability has a significant positive impact on big data human capability. (3) Big data system capability and big data management capability have a significant positive effect on smart service performance. (4) The impact of big data human capability on smart service performance is not however significant enough to bring about the improvements which the government seeks.INDEX TERMS Big data system capabilities, big data human capabilities, big data management capabilities, smart service performance, structural equation model.

The Cognitive Radio (CR) technology is an efficient solution to spectrum scarcity by share the spectrum with the secondary users on a non-interfering basis. The spectrum prediction can rationalize the spectrum allocation based on previous information about the spectrum evolution in time. Against previous spectrum prediction algorithm lack of timeliness and accuracy, this paper proposes a novel approach for spectrum prediction based on Optimally Pruned Extreme Learning Machine (OP-ELM) which improved the original Extreme Learning Machine (ELM) algorithm. This method not only takes the advantage of the ELM extremely fast speed and good precision, but also more robust and generic with additional steps compared with ELM. In order to compare its comprehensive properties to other algorithms, some experiments were designed. The results show that the predictive performance of this new algorithm is more satisfaction than others in spectrum prediction problem.

This paper addresses the problem of fast similar image retrieval, especially for large-scale datasets with millions of images. We present a new framework which consists of two dependent algorithms. First, a new feature is proposed to represent images, which is dubbed compact feature based clustering(CFC). For each image, we first extract cluster centers of local features, and then calculate distribution histograms of local features and statistics of spatial information in each cluster to form compact features based clustering, replacing thousands of local features. It can reduce feature vectors of image representation and enhance the discriminative power of each feature. In addition, an efficient retrieval method is proposed, based on vocabulary tree through compact features based clustering. Extensive experiments on the Ukbench, Holidays, and ImageNet databases demonstrate that our method reduces the memory and computation overhead and improves the retrieval efficiency, while keeping approximate state-of-the-art accuracy.

No abstract